Action recognition using invariant features under unexampled viewing conditions

A great challenge in real-world applications of action recognition is the lack of sufficient label information because of variance in the recording viewpoint and differences between individuals. A system that can adapt itself according to these variances is required for practical use. We present a generic method for extracting view-invariant features from skeleton joints. These view-invariant features are further refined using a stacked, compact autoencoder. To model the challenge of real-world applications, two unexampled test settings (NewView and NewPerson) are used to evaluate the proposed method. Experimental results with these test settings demonstrate the effectiveness of our method.